* Add WIP Monitored wrapper
* Remove irrelevant render after close monitor test
* py27 compatibility
* Fix test_benchmark
* Move Monitored out of wrappers __init__
* Turn Monitored into a function that returns a Monitor class
* Fix monitor tests
* Remove deprecated test
* Remove deprecated utility
* Prevent duplicate wrapping, add test
* Fix test
* close env in tests to prevent writing to nonexistent file
* Disable semisuper tests
* typo
* Fix failing spec
* Fix monitoring on semisuper tasks
* Allow disabling of duplicate check
* Rename MonitorManager
* Monitored -> Monitor
* Clean up comments
* Remove cruft
* added continuous mountain car v0
* spotted that the action should be a vector, not a scalar
* fixed bug on action format
* bug fixed in scoreboard registering
* the observation (aka state) should be a numpy array
* added comment on reward range as requested
* Tweak README and don't use __new__ for wrapper
The extra 'env' argument means that Wrapper authors with a custom
__init__ need to think about the parent signature anyway, so there's
not as much benefit to adding the more surprising __new__.
* Add support for registering wrappers for the official environment
* Wrappers - Added 'wrappers' and 'step_count' property + monitor support
* Removed step_count and wrappers from api and monitor
* Removed wrappers and name property
* Add configure method to Env, and support multiple displays in CartPole
This allows people to pass runtime specification which doesn't affect
the environment semantics to environments created via `make`.
Also include an example of setting the display used for CartPole
* Provide full configure method
* Allow environments to require configuration
* Don't take arguments in make
* Make environments seedable
* Fix monitor bugs
- Set monitor_id before setting the infix. This was a bug that would yield incorrect results with multiple monitors.
- Remove extra pid from stats recorder filename. This should be purely cosmetic.
* Start uploading seeds in episode_batch
* Fix _bigint_from_bytes for python3
* Set seed explicitly in random_agent
* Pass through seed argument
* Also pass through random state to spaces
* Pass random state into the observation/action spaces
* Make all _seed methods return the list of used seeds
* Switch over to np.random where possible
* Start hashing seeds, and also seed doom engine
* Fixup seeding determinism in many cases
* Seed before loading the ROM
* Make seeding more Python3 friendly
* Make the MuJoCo skipping a bit more forgiving
* Remove debugging PDB calls
* Make setInt argument into raw bytes
* Validate and upload seeds
* Skip box2d
* Make seeds smaller, and change representation of seeds in upload
* Handle long seeds
* Fix RandomAgent example to be deterministic
* Handle integer types correctly in Python2 and Python3
* Try caching pip
* Try adding swap
* Add df and free calls
* Bump swap
* Bump swap size
* Try setting overcommit
* Try other sysctls
* Try fixing overcommit
* Try just setting overcommit_memory=1
* Add explanatory comment
* Add what's new section to readme
* BUG: Mark ElevatorAction-ram-v0 as non-deterministic for now
* Document seed
* Move nondetermistic check into spec
* Improve auto close implementation
- Register all envs at initialization time, not just ones created via make
- Simplify names and add more documentation on interface
- Move closer instances into the relevant modules
review-requested: @jietang
* Close environments in the tests
This isn't strictly needed, but means there are fewer Doom
subprocesses hanging around while the tests run.
* Use 4 space indent in comment
* Improve docstrings in core
* Don't pass through args to __new__
The __init__ method gets called once __new__ returns,
so these arguments are either ignored (Python 2) or
result in an error (Python 3). The __init__ method
automatically gets called with the correct arguments.
* Fixup comments
* Set restriction on selected actions
* Used self.action_space instead of custom set
* Move action validation to core.py
* Fix for Cartpole observations outside of observation_space
* Fix observation_space for Bipedal_walker and add warning if observation doesn't fit observation_space
* Remove observation state check on reset.
Multiple environments call reset before action and observation spaces
are initialized.
